https://sam.ensam.eu:443 The DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material. Mon, 13 Apr 2026 01:50:06 GMT 2026-04-13T01:50:06Z http://hdl.handle.net/10985/15357 A finite element/quaternion/asymptotic numerical method for the 3D simulation of flexible cables COTTANCEAU, Emmanuel; THOMAS, Olivier; VÉRON, Philippe; ALOCHET, Marc; DELIGNY, Renaud In this paper, a method for the quasi-static simulation of flexible cables assembly in the context of automotive industry is presented. The cables geometry and behavior encourage to employ a geometrically exact beam model. The 3D kinematics is then based on the position of the centerline and on the orientation of the cross-sections, which is here represented by rotational quaternions. Their algebraic nature leads to a polynomial form of equilibrium equations. The continuous equations obtained are then discretized by the finite element method and easily recast under quadratic form by introducing additional slave variables. The asymptotic numerical method, a powerful solver for systems of quadratic equations, is then employed for the continuation of the branches of solution. The originality of this paper stands in the combination of all these methods which leads to a fast and accurate tool for the assembly process of cables. This is proved by running several classical validation tests and an industry-like example. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10985/15357 2018-01-01T00:00:00Z COTTANCEAU, Emmanuel THOMAS, Olivier VÉRON, Philippe ALOCHET, Marc DELIGNY, Renaud In this paper, a method for the quasi-static simulation of flexible cables assembly in the context of automotive industry is presented. The cables geometry and behavior encourage to employ a geometrically exact beam model. The 3D kinematics is then based on the position of the centerline and on the orientation of the cross-sections, which is here represented by rotational quaternions. Their algebraic nature leads to a polynomial form of equilibrium equations. The continuous equations obtained are then discretized by the finite element method and easily recast under quadratic form by introducing additional slave variables. The asymptotic numerical method, a powerful solver for systems of quadratic equations, is then employed for the continuation of the branches of solution. The originality of this paper stands in the combination of all these methods which leads to a fast and accurate tool for the assembly process of cables. This is proved by running several classical validation tests and an industry-like example. http://hdl.handle.net/10985/17675 Understanding the relationships between aesthetic properties and geometric quantities of free-form surfaces using machine learning techniques PETROV, Aleksandar; GIANNINI, Franca; VÉRON, Philippe; FALCIDIENO, Bianca; PERNOT, Jean-Philippe Designing appealing products plays a key role in commercial success. Understanding the relationships between aesthetic properties and shape characteristics of a product can contribute to define user-friendly and interactive designing tools supporting the early design phases. This paper introduces a generic framework for mapping aesthetic properties to 3D free form shapes. The approach uses machine learning techniques to identify rules between the user-defined classifications of shapes and the geometric parameters of the underlying free form surfaces and to create an efficient classification model. The framework has been set up and validated focusing on the flatness aesthetic property but is generic and can be applied to others. Several experiments have been conducted to understand if there is a consistency among people in the judgement of a specific aesthetic properties, if and to which extent the surrounding of the judged surface affects the perception consistency, and which are the surface geometric quantities influencing the perception. A graphic user interface has been designed to allow a fast classification of thousands of shapes automatically generated. The experiments have been conducted following a systematic methodology comparing two different approaches. The results confirm that the perception of flatness is commonly shared by the majority and the most relevant attributes have been identified. Additionally, it results that the surrounding information extension and context influence the perception of the flatness strengthening the classification consistency. The way those results can be used to design new interactive tools and to improve the product design process is discussed. Tue, 01 Jan 2019 00:00:00 GMT http://hdl.handle.net/10985/17675 2019-01-01T00:00:00Z PETROV, Aleksandar GIANNINI, Franca VÉRON, Philippe FALCIDIENO, Bianca PERNOT, Jean-Philippe Designing appealing products plays a key role in commercial success. Understanding the relationships between aesthetic properties and shape characteristics of a product can contribute to define user-friendly and interactive designing tools supporting the early design phases. This paper introduces a generic framework for mapping aesthetic properties to 3D free form shapes. The approach uses machine learning techniques to identify rules between the user-defined classifications of shapes and the geometric parameters of the underlying free form surfaces and to create an efficient classification model. The framework has been set up and validated focusing on the flatness aesthetic property but is generic and can be applied to others. Several experiments have been conducted to understand if there is a consistency among people in the judgement of a specific aesthetic properties, if and to which extent the surrounding of the judged surface affects the perception consistency, and which are the surface geometric quantities influencing the perception. A graphic user interface has been designed to allow a fast classification of thousands of shapes automatically generated. The experiments have been conducted following a systematic methodology comparing two different approaches. The results confirm that the perception of flatness is commonly shared by the majority and the most relevant attributes have been identified. Additionally, it results that the surrounding information extension and context influence the perception of the flatness strengthening the classification consistency. The way those results can be used to design new interactive tools and to improve the product design process is discussed. http://hdl.handle.net/10985/19955 Lightweight Mesh File Format Using Repetition Pattern Encoding for Additive Manufacturing VAISSIER, Benjamin; CHOUGRANI, Laurent; VÉRON, Philippe; PERNOT, Jean-Philippe To facilitate the transfer, storage and manipulation of intricate parts’ geometry whose fabrication has been made possible thanks to the rise of Additive Manufacturing (AM) technologies, an encoding framework reducing the resulting file size has been developed. This approach leverages the fact that many AM parts are presenting repetition patterns, by encoding the repetition of similar geometry chunks. The decomposition of the part into chunks is a complex optimization problem, whose identification as a Weighted Exact Cover (WEC) problem allowed to develop a new heuristic algorithm dedicated to its fast resolution in linear time . The encoding strategy is implemented through a variation of the AMF file standard (for quick adoption of the format by existing software), and also through a new ad-hoc hybrid file format. To demonstrate the efficiency of the approach, the encryption of lattice and support structures through these two encoding strategies are compared to the results of several state-of-the-art encoding approaches. The way this data weight lightening strategy preserves the overall accuracy is discussed while considering different floating points encoding precisions with respect to the AM process requirements. This comparison exhibits file size reductions up to -84% in comparison with file sizes generated by state-of-the-art approaches. Not only the proposed repetition pattern encoding framework allows file size reductions, but it could also be exploited to optimize and speed-up some steps of the Product Development Process (PDP), including process planning phases. Wed, 01 Jan 2020 00:00:00 GMT http://hdl.handle.net/10985/19955 2020-01-01T00:00:00Z VAISSIER, Benjamin CHOUGRANI, Laurent VÉRON, Philippe PERNOT, Jean-Philippe To facilitate the transfer, storage and manipulation of intricate parts’ geometry whose fabrication has been made possible thanks to the rise of Additive Manufacturing (AM) technologies, an encoding framework reducing the resulting file size has been developed. This approach leverages the fact that many AM parts are presenting repetition patterns, by encoding the repetition of similar geometry chunks. The decomposition of the part into chunks is a complex optimization problem, whose identification as a Weighted Exact Cover (WEC) problem allowed to develop a new heuristic algorithm dedicated to its fast resolution in linear time . The encoding strategy is implemented through a variation of the AMF file standard (for quick adoption of the format by existing software), and also through a new ad-hoc hybrid file format. To demonstrate the efficiency of the approach, the encryption of lattice and support structures through these two encoding strategies are compared to the results of several state-of-the-art encoding approaches. The way this data weight lightening strategy preserves the overall accuracy is discussed while considering different floating points encoding precisions with respect to the AM process requirements. This comparison exhibits file size reductions up to -84% in comparison with file sizes generated by state-of-the-art approaches. Not only the proposed repetition pattern encoding framework allows file size reductions, but it could also be exploited to optimize and speed-up some steps of the Product Development Process (PDP), including process planning phases. http://hdl.handle.net/10985/19988 A Property Graph Data Model for a Context-Aware Design Assistant PINQUIÉ, Romain; VÉRON, Philippe; ZYNDA, Thomas; SEGONDS, Frederic The design of a product requires to satisfy a large number of design rules so as to avoid design errors. [Problem] Although there are numerous technological alternatives for managing knowledge, design departments continue to store design rules in nearly unusable documents. Indeed, existing propositions based on basic information retrieval techniques applied to unstructured engineering documents do not provide good results. Conversely, the development and management of structured ontologies are too laborious. [Proposition] We propose a property graph data model that paves the way to a context-aware design assistant. The property graph data model is a graph-oriented data structure that enables us to formally define a design context as a consolidated set of five sub-contexts: social, semantic, engineering, operational IT, and traceability. [Future work] Connected to or embedded in a Computer Aided Design (CAD) environment, our context-aware design assistant will extend traditional CAD capabilities as it could, for instance, ease: 1) the retrieval of rules according to a particular design context, 2) the recommendation of design rules while a design activity is being performed, 3) the verification of design solutions, 4) the automation of design routines, etc. Wed, 01 Jan 2020 00:00:00 GMT http://hdl.handle.net/10985/19988 2020-01-01T00:00:00Z PINQUIÉ, Romain VÉRON, Philippe ZYNDA, Thomas SEGONDS, Frederic The design of a product requires to satisfy a large number of design rules so as to avoid design errors. [Problem] Although there are numerous technological alternatives for managing knowledge, design departments continue to store design rules in nearly unusable documents. Indeed, existing propositions based on basic information retrieval techniques applied to unstructured engineering documents do not provide good results. Conversely, the development and management of structured ontologies are too laborious. [Proposition] We propose a property graph data model that paves the way to a context-aware design assistant. The property graph data model is a graph-oriented data structure that enables us to formally define a design context as a consolidated set of five sub-contexts: social, semantic, engineering, operational IT, and traceability. [Future work] Connected to or embedded in a Computer Aided Design (CAD) environment, our context-aware design assistant will extend traditional CAD capabilities as it could, for instance, ease: 1) the retrieval of rules according to a particular design context, 2) the recommendation of design rules while a design activity is being performed, 3) the verification of design solutions, 4) the automation of design routines, etc. http://hdl.handle.net/10985/19986 A requirement mining framework to support complex sub-systems suppliers PINQUIÉ, Romain; VÉRON, Philippe; CROUÉ, Nicolas; SEGONDS, Frederic The design of engineered socio-technical systems relies on a value chain within which suppliers must cope with larger and larger sets of requirements. Although 70 % of the total life cycle cost is committed during the concept phase and most industrial projects originally fail due to poor requirements engineering [1], very few methods and tools exist to support suppliers. In this paper, we propose to methodologically integrate data science techniques into a collaborative requirement mining framework so as to enable suppliers to gain insight and discover opportunities in a massive set of requirements. The proposed workflow is a five-phase process including: (1) the extraction of requirements from documents and (2) the analysis of their quality by using natural language processing techniques; (3) the segmentation of requirements into communities using text mining and graph theory; (4) the collaborative and multidisciplinary estimation of decision making criteria; and (5) the reporting of estimations via an analytical dashboard of statistical indicators. We conclude that the methodological integration of data science techniques is an effective way to gain insight from hundreds or thousands of requirements before making informed decisions early on. The software prototype that supports our workflow is a JAVA web application developed on top of a graph-oriented data model implemented with the NoSQL NEO4J graph database. As a future work, the semi-structured as-required baseline could be a sound input to feed a formal approach, such as model- and simulation-based systems engineering. Mon, 01 Jan 2018 00:00:00 GMT http://hdl.handle.net/10985/19986 2018-01-01T00:00:00Z PINQUIÉ, Romain VÉRON, Philippe CROUÉ, Nicolas SEGONDS, Frederic The design of engineered socio-technical systems relies on a value chain within which suppliers must cope with larger and larger sets of requirements. Although 70 % of the total life cycle cost is committed during the concept phase and most industrial projects originally fail due to poor requirements engineering [1], very few methods and tools exist to support suppliers. In this paper, we propose to methodologically integrate data science techniques into a collaborative requirement mining framework so as to enable suppliers to gain insight and discover opportunities in a massive set of requirements. The proposed workflow is a five-phase process including: (1) the extraction of requirements from documents and (2) the analysis of their quality by using natural language processing techniques; (3) the segmentation of requirements into communities using text mining and graph theory; (4) the collaborative and multidisciplinary estimation of decision making criteria; and (5) the reporting of estimations via an analytical dashboard of statistical indicators. We conclude that the methodological integration of data science techniques is an effective way to gain insight from hundreds or thousands of requirements before making informed decisions early on. The software prototype that supports our workflow is a JAVA web application developed on top of a graph-oriented data model implemented with the NoSQL NEO4J graph database. As a future work, the semi-structured as-required baseline could be a sound input to feed a formal approach, such as model- and simulation-based systems engineering. http://hdl.handle.net/10985/23421 H-BIM and Artificial Intelligence: Classification of Architectural Heritage for Semi-Automatic Scan-to-BIM Reconstruction CROCE, Valeria; CAROTI, Gabriella; PIEMONTE, Andrea; DE LUCA, Livio; VÉRON, Philippe We propose a semi-automatic Scan-to-BIM reconstruction approach, making the most of Artificial Intelligence (AI) techniques, for the classification of digital architectural heritage data. Nowadays, Heritage- or Historic-Building Information Modeling (H-BIM) reconstruction from laser scanning or photogrammetric surveys is a manual, time-consuming, overly subjective process, but the emergence of AI techniques, applied to the realm of existing architectural heritage, is offering new ways to interpret, process and elaborate raw digital surveying data, as point clouds. The proposed methodological approach for higher-level automation in Scan-to-BIM reconstruction is threaded as follows: (i) semantic segmentation via Random Forest and import of annotated data in 3D modeling environment, broken down class by class; (ii) reconstruction of template geometries of classes of architectural elements; (iii) propagation of template reconstructed geometries to all elements belonging to a typological class. Visual Programming Languages (VPLs) and reference to architectural treatises are leveraged for the Scan-to-BIM reconstruction. The approach is tested on several significant heritage sites in the Tuscan territory, including charterhouses and museums. The results suggest the replicability of the approach to other case studies, built in different periods, with different construction techniques or under different states of conservation. Thu, 23 Feb 2023 00:00:00 GMT http://hdl.handle.net/10985/23421 2023-02-23T00:00:00Z CROCE, Valeria CAROTI, Gabriella PIEMONTE, Andrea DE LUCA, Livio VÉRON, Philippe We propose a semi-automatic Scan-to-BIM reconstruction approach, making the most of Artificial Intelligence (AI) techniques, for the classification of digital architectural heritage data. Nowadays, Heritage- or Historic-Building Information Modeling (H-BIM) reconstruction from laser scanning or photogrammetric surveys is a manual, time-consuming, overly subjective process, but the emergence of AI techniques, applied to the realm of existing architectural heritage, is offering new ways to interpret, process and elaborate raw digital surveying data, as point clouds. The proposed methodological approach for higher-level automation in Scan-to-BIM reconstruction is threaded as follows: (i) semantic segmentation via Random Forest and import of annotated data in 3D modeling environment, broken down class by class; (ii) reconstruction of template geometries of classes of architectural elements; (iii) propagation of template reconstructed geometries to all elements belonging to a typological class. Visual Programming Languages (VPLs) and reference to architectural treatises are leveraged for the Scan-to-BIM reconstruction. The approach is tested on several significant heritage sites in the Tuscan territory, including charterhouses and museums. The results suggest the replicability of the approach to other case studies, built in different periods, with different construction techniques or under different states of conservation. http://hdl.handle.net/10985/19975 From the Semantic Point Cloud to Heritage-Building Information Modeling: A Semiautomatic Approach Exploiting Machine Learning CROCE, Valeria; CAROTI, Gabriella; DE LUCA, Livio; JACQUOT, Kévin; PIEMONTE, Andrea; VÉRON, Philippe This work presents a semi-automatic approach to the 3D reconstruction of Heritage-Building Information Models from point clouds based on machine learning techniques. The use of digital information systems leveraging on three-dimensional (3D) representations in architectural heritage documentation and analysis is ever increasing. For the creation of such repositories, reality-based surveying techniques, such as photogrammetry and laser scanning, allow the fast collection of reliable digital replicas of the study objects in the form of point clouds. Besides, their output is raw and unstructured, and the transition to intelligible and semantic 3D representations is still a scarcely automated and time-consuming process requiring considerable human intervention. More refined methods for 3D data interpretation of heritage point clouds are therefore sought after. In tackling these issues, the proposed approach relies on (i) the application of machine learning techniques to semantically label 3D heritage data by identification of relevant geometric, radiometric and intensity features, and (ii) the use of the annotated data to streamline the construction of Heritage-Building Information Modeling (H-BIM) systems, where purely geometric information derived from surveying is associated with semantic descriptors on heritage documentation and management. The “Grand-Ducal Cloister” dataset, related to the emblematic case study of the Pisa Charterhouse, is discussed. Fri, 01 Jan 2021 00:00:00 GMT http://hdl.handle.net/10985/19975 2021-01-01T00:00:00Z CROCE, Valeria CAROTI, Gabriella DE LUCA, Livio JACQUOT, Kévin PIEMONTE, Andrea VÉRON, Philippe This work presents a semi-automatic approach to the 3D reconstruction of Heritage-Building Information Models from point clouds based on machine learning techniques. The use of digital information systems leveraging on three-dimensional (3D) representations in architectural heritage documentation and analysis is ever increasing. For the creation of such repositories, reality-based surveying techniques, such as photogrammetry and laser scanning, allow the fast collection of reliable digital replicas of the study objects in the form of point clouds. Besides, their output is raw and unstructured, and the transition to intelligible and semantic 3D representations is still a scarcely automated and time-consuming process requiring considerable human intervention. More refined methods for 3D data interpretation of heritage point clouds are therefore sought after. In tackling these issues, the proposed approach relies on (i) the application of machine learning techniques to semantically label 3D heritage data by identification of relevant geometric, radiometric and intensity features, and (ii) the use of the annotated data to streamline the construction of Heritage-Building Information Modeling (H-BIM) systems, where purely geometric information derived from surveying is associated with semantic descriptors on heritage documentation and management. The “Grand-Ducal Cloister” dataset, related to the emblematic case study of the Pisa Charterhouse, is discussed. http://hdl.handle.net/10985/20716 i-Dataquest: A heterogeneous information retrieval tool using data graph for the manufacturing industry KIM, Lise; YAHIA, Esma; SEGONDS, Frederic; VÉRON, Philippe; MALLET, Antoine Manufacturing industry needs access to the data in order to realise its activities but also to generate new value-added knowledge. Nevertheless, it is confronted with a large and growing volume of heterogeneous data which limits its ability to exploit them optimally. Moreover, the data are distributed within different heterogeneous information systems, which limits the relationship exploration under the information retrieval process. Usually, the challenge is addressed by trying to manage and normalize the data structure in order to faster searching and exploiting them in a manufacturing context. For their part, the authors present i-Dataquest, an information retrieval system supported by (i) a graph-oriented model built from the structured and unstructured data of the company and (ii) a query system answering ‘what’ and ‘about what’ and (iii) generating three different results: a list of items, a list of property values and a list of sentences. The i-Dataquest prototype is built using Neo4J for the graph system generation, ConceptNet for lexical resource management and StandfordNLP for natural language processing. An evaluation of the prototype’s performance is conducted through a data set representing a drone manufacturer. The results show that the transformation of specific content such as tables in the graph and the semantic expansion of queries significantly improves the recall and precision measures. The results also suggest improving filtering less relevant results by considering particularly queries looking for a specific value. Sun, 01 Jan 2023 00:00:00 GMT http://hdl.handle.net/10985/20716 2023-01-01T00:00:00Z KIM, Lise YAHIA, Esma SEGONDS, Frederic VÉRON, Philippe MALLET, Antoine Manufacturing industry needs access to the data in order to realise its activities but also to generate new value-added knowledge. Nevertheless, it is confronted with a large and growing volume of heterogeneous data which limits its ability to exploit them optimally. Moreover, the data are distributed within different heterogeneous information systems, which limits the relationship exploration under the information retrieval process. Usually, the challenge is addressed by trying to manage and normalize the data structure in order to faster searching and exploiting them in a manufacturing context. For their part, the authors present i-Dataquest, an information retrieval system supported by (i) a graph-oriented model built from the structured and unstructured data of the company and (ii) a query system answering ‘what’ and ‘about what’ and (iii) generating three different results: a list of items, a list of property values and a list of sentences. The i-Dataquest prototype is built using Neo4J for the graph system generation, ConceptNet for lexical resource management and StandfordNLP for natural language processing. An evaluation of the prototype’s performance is conducted through a data set representing a drone manufacturer. The results show that the transformation of specific content such as tables in the graph and the semantic expansion of queries significantly improves the recall and precision measures. The results also suggest improving filtering less relevant results by considering particularly queries looking for a specific value. http://hdl.handle.net/10985/23383 Smartphone LiDAR Data: A Case Study for Numerisation of Indoor Buildings in Railway Stations CATHARIA, Orphé; RICHARD, Franck; VIGNOLES, Henri; VÉRON, Philippe; SEGONDS, Frederic; AOUSSAT, Améziane The combination of LiDAR with other technologies for numerisation is increasingly applied in the field of building, design, and geoscience, as it often brings time and cost advantages in 3D data survey processes. In this paper, the reconstruction of 3D point cloud datasets is studied, through an experimental protocol evaluation of new LiDAR sensors on smartphones. To evaluate and analyse the 3D point cloud datasets, different experimental conditions are considered depending on the acquisition mode and the type of object or surface being scanned. The conditions allowing us to obtain the most accurate data are identified and used to propose which acquisition protocol to use. This protocol seems to be the most adapted when using these LiDAR sensors to digitise complex interior buildings such as railway stations. This paper aims to propose: (i) a methodology to suggest the adaptation of an experimental protocol based on factors (distance, luminosity, surface, time, and incidence) to assess the precision and accuracy of the smartphone LiDAR sensor in a controlled environment; (ii) a comparison, both qualitative and quantitative, of smartphone LiDAR data with other traditional 3D scanner alternatives (Faro X130, VLX, and Vz400i) while considering three representative building interior environments; and (iii) a discussion of the results obtained in a controlled and a field environment, making it possible to propose recommendations for the use of the LiDAR smartphone at the end of the numerisation of the interior space of a building. Thu, 09 Feb 2023 00:00:00 GMT http://hdl.handle.net/10985/23383 2023-02-09T00:00:00Z CATHARIA, Orphé RICHARD, Franck VIGNOLES, Henri VÉRON, Philippe SEGONDS, Frederic AOUSSAT, Améziane The combination of LiDAR with other technologies for numerisation is increasingly applied in the field of building, design, and geoscience, as it often brings time and cost advantages in 3D data survey processes. In this paper, the reconstruction of 3D point cloud datasets is studied, through an experimental protocol evaluation of new LiDAR sensors on smartphones. To evaluate and analyse the 3D point cloud datasets, different experimental conditions are considered depending on the acquisition mode and the type of object or surface being scanned. The conditions allowing us to obtain the most accurate data are identified and used to propose which acquisition protocol to use. This protocol seems to be the most adapted when using these LiDAR sensors to digitise complex interior buildings such as railway stations. This paper aims to propose: (i) a methodology to suggest the adaptation of an experimental protocol based on factors (distance, luminosity, surface, time, and incidence) to assess the precision and accuracy of the smartphone LiDAR sensor in a controlled environment; (ii) a comparison, both qualitative and quantitative, of smartphone LiDAR data with other traditional 3D scanner alternatives (Faro X130, VLX, and Vz400i) while considering three representative building interior environments; and (iii) a discussion of the results obtained in a controlled and a field environment, making it possible to propose recommendations for the use of the LiDAR smartphone at the end of the numerisation of the interior space of a building. http://hdl.handle.net/10985/23382 Challenges for data-driven design in early physical product design: A scientific and industrial perspective BRIARD, Tristan; JEAN, Camille; VÉRON, Philippe; AOUSSAT, Améziane With the rapid development of digital technologies, complex products are becoming more connected. Alongside, the usage of data in the product development process keeps on increasing. Data is an essential means of monitoring the behaviour of the products and their users for optimisation purposes. It is in the digital sector that data is already commonly used to identify new opportunities, to support decision-making and to reduce development time. To replicate this process with physical products, novel design approaches based on data are emerging. Designers need to anticipate from the early stages of product design the right data to capture and analyse. However, research is still in its infancy and faces numerous challenges. Thus, the question addressed in this article is: “what are the challenges of data-driven design research in the early phases of the physical product development process?” A workshop involving 10 researchers was held to answer this question. In addition, a campaign of 12 interviews with connected products manufacturers completed this research. Through a literature review, the workshop and the campaign of interviews, this article synthesizes both a scientific and an industrial outlook on the challenges of data driven design. It offers a first glimpse of future research leads. Wed, 01 Feb 2023 00:00:00 GMT http://hdl.handle.net/10985/23382 2023-02-01T00:00:00Z BRIARD, Tristan JEAN, Camille VÉRON, Philippe AOUSSAT, Améziane With the rapid development of digital technologies, complex products are becoming more connected. Alongside, the usage of data in the product development process keeps on increasing. Data is an essential means of monitoring the behaviour of the products and their users for optimisation purposes. It is in the digital sector that data is already commonly used to identify new opportunities, to support decision-making and to reduce development time. To replicate this process with physical products, novel design approaches based on data are emerging. Designers need to anticipate from the early stages of product design the right data to capture and analyse. However, research is still in its infancy and faces numerous challenges. Thus, the question addressed in this article is: “what are the challenges of data-driven design research in the early phases of the physical product development process?” A workshop involving 10 researchers was held to answer this question. In addition, a campaign of 12 interviews with connected products manufacturers completed this research. Through a literature review, the workshop and the campaign of interviews, this article synthesizes both a scientific and an industrial outlook on the challenges of data driven design. It offers a first glimpse of future research leads.